Yazar "Tezel, Guelay" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    A new approach for classification of EEG signals
    (IEEE, 2007) Tezel, Guelay; Ozbay, Yueksel
    This study presents a comparative study of the classification accuracy and speed of performance of epileptic Electroensefalogram (EEG) signals using a traditional neural network architecture based on backpropagation training algorithm, and a new neural network. The proposed network is called adaptive neural network with activation function (AAF-NN) in which adjustable parameters, It is used two different activation functions for developed study. One of theese adaptive activation functions is sigmoid function with free parameters and the other one is sum of sinusoidal function with free parameters and sigmoid function with free parameters. The adaptive activation function with free parameters is used in the hidden layer for the proposed structures based on the feed-forward neural network Experimental results have revealed that neural network with adaptive activation function is more suitable for classification EEG signals and training speed is much faster than traditional neural network with fixed sigmoid activation function.
  • Küçük Resim Yok
    Öğe
    A new approach for epileptic seizure detection using adaptive
    (PERGAMON-ELSEVIER SCIENCE LTD, 2009) Tezel, Guelay; Ozbay, Yuksel
    This paper presents new neural network models with adaptive activation function (NNAAF) to detect epileptic seizure. Our NNAAF models included three types named as NNAAF-1, NNAAF-2 and NNAAF-3. The activation function of hidden neuron in the model of NNAAF-1 is sigmoid function with free parameters. In the second model, NNAAF-2, activation function of hidden neuron is sum of sigmoid function with free parameters and sinusoidal function with free parameters. In the third model, NNAAF-3, hidden neurons' activation function is Morlet Wavelet function with free parameters. In addition, we implemented traditional multilayer perceptron (MLP) neural network (NN) model with. fixed sigmoid activation function in the hidden layer to compare NNAAF models. The proposed models were trained and tested using 5-fold cross-validation to prove robustness of these models and to. find the best model. We achieved 100% average sensitivity, average specificity, and approximately 100% average classification rate in all the models. It was seen that their speeds and the number of maximum iteration were changed for each model. The training time and the number of maximum iteration were reduced on about 50% using NNAAF-3 model. Hence it can be remarkable that NNAAF-3 is more suitable than the other models for real-time application. (C) 2007 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    A new neural network with adaptive activation function for classification of ECG Arrhythmias
    (SPRINGER-VERLAG BERLIN, 2007) Tezel, Guelay; Oezbay, Yueksel
    This study presents a comparative study of the classification accuracy of ECG signals using a well-known neural network architecture named multilayered perception (MLP) with backpropagation training algorithm, and a new neural network with adaptive activation function (AAFNN) for classification of ECG arrhythmias. The ECG signals are taken from MIT-BIH ECG database, which are used to classify ten different arrhythmias for training. These are normal sinus rhythm, sinus bradycardia, ventricular tachycardia, sinus arrhythmia, atrial premature contraction, paced beat, right bundle branch block, left bundle branch block, atrial fibrillation and atrial flutter. For testing, the proposed structures were trained by backpropagation algorithm. Both of them tested using experimental ECG records of 10 patients (7 male and 3 female, average age is 33.8 +/- 16.4). The results show that neural network with adaptive activation function is more suitable for biomedical data like as ECG in the classification problems and training speed is much faster than neural network with fixed sigmoid activation function
  • Küçük Resim Yok
    Öğe
    THE STRUCTURE AND ADVANTAGES OF DIGITAL TRAINING SET FOR COMPUTER ENGINEERING
    (WORLD SCIENTIFIC AND ENGINEERING ACAD AND SOC, 2009) Tezel, Guelay; Kahramanli, Sirzat
    The knowledge provided in theoretical computer engineering education needs to be tested in laboratory which contributes to acquiring of specifications on tools, equipment and measurement methods. During the laboratory classes, using specifically produced experimental sets reduce cost and learning time developing the designing ability of students. The theoretical courses are supported with digital design and microprocessor courses in electronics and computer education, where the fundamentals of computer hardware and digital control technologies are provided. In the present study, the established Digital Training Set (DTS) and Microcontroller 8031, and their advantages in experimentally teaching and learning of basic digital circuits design and principles of microprocessors in the Computer Engineering Department of Selcuk University are presented.